Deep RegNet-150 architecture for single image super resolution of real-time unpaired image data

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 162, P. 111837 - 111837

Published: June 15, 2024

Language: Английский

---

Diffusion Models, Image Super-Resolution, and Everything: A Survey

IEEE Transactions on Neural Networks and Learning Systems, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 21

Published: Jan. 1, 2024

Diffusion Models (DMs) have disrupted the image Super-Resolution (SR) field and further closed gap between quality human perceptual preferences.They are easy to train can produce very high-quality samples that exceed realism of those produced by previous generative methods.Despite their promising results, they also come with new challenges need research: high computational demands, comparability, lack explainability, color shifts, more.Unfortunately, entry into this is overwhelming because abundance publications.To address this, we provide a unified recount theoretical foundations underlying DMs applied SR offer detailed analysis underscores unique characteristics methodologies within domain, distinct from broader existing reviews in field.This survey articulates cohesive understanding DM principles explores current research avenues, including alternative input domains, conditioning techniques, guidance mechanisms, corruption spaces, zero-shot learning approaches.By offering examination evolution trends through lens DMs, sheds light on charts potential future directions, aiming inspire innovation rapidly advancing area.

Language: Английский

---

Multi-depth branch network for efficient image super-resolution

Image and Vision Computing, Journal Year: 2024, Volume and Issue: 144, P. 104949 - 104949

Published: Feb. 18, 2024

Language: Английский

---

Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution

2022 International Joint Conference on Neural Networks (IJCNN), Journal Year: 2024, Volume and Issue: 14, P. 1 - 8

Published: June 30, 2024

Language: Английский

---

Activating More Information in Arbitrary-Scale Image Super-Resolution

IEEE Transactions on Multimedia, Journal Year: 2024, Volume and Issue: 26, P. 7946 - 7961

Published: Jan. 1, 2024

Single-image super-resolution (SISR) has experienced vigorous growth with the rapid development of deep learning. However, handling arbitrary scales ( e.g., integers, non-integers, or asymmetric) using a single model remains challenging task. Existing (SR) networks commonly employ static convolutions during feature extraction, which cannot effectively perceive changes in scales. Moreover, these continuous-scale upsampling modules only utilize scale factors, without considering diversity local features. To activate more information for better reconstruction, two plug-in and compatible fixed-scale are designed to perform arbitrary-scale SR tasks. Firstly, we design Scale-aware Local Feature Adaptation Module (SLFAM), adaptively adjusts attention weights dynamic filters based on features It enables network possess stronger representation capabilities. Then propose Upsampling (LFAUM), combines reconstruction. allows adapt structures. Besides, deformable convolution is utilized letting be activated enabling texture Extensive experiments various benchmark datasets demonstrate that integrating proposed into it achieve satisfactory results non-integer asymmetric while maintaining advanced performance integer

Language: Английский

---

Lightweight Efficient Rate-Adaptive Network for Compression-Aware Image Rescaling

IEEE Signal Processing Letters, Journal Year: 2025, Volume and Issue: 32, P. 691 - 695

Published: Jan. 1, 2025

Language: Английский

---

PCCN: Polarimetric Contexture Convolutional Network for PolSAR Image Super-Resolution

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Journal Year: 2025, Volume and Issue: 18, P. 4664 - 4679

Published: Jan. 1, 2025

Language: Английский

---

Computational Super-Resolution: An Odyssey in Harnessing Priors to Enhance Optical Microscopy Resolution

Analytical Chemistry, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 27, 2025

Language: Английский

---

Image Superresolution in Single-Pixel Imaging with Generative Adversarial Networks

Bulletin of the Lebedev Physics Institute, Journal Year: 2025, Volume and Issue: 52(1), P. 14 - 21

Published: Jan. 1, 2025

Language: Английский

---

A review of deep learning for super-resolution in fluid flows

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(4)

Published: April 1, 2025

Integrating deep learning with fluid dynamics presents a promising path for advancing the comprehension of complex flow phenomena within both theoretical and practical engineering domains. Despite this potential, considerable challenges persist, particularly regarding calibration training models. This paper conducts an extensive review analysis recent developments in architectures that aim to enhance accuracy data interpretation. It investigates various applications, architectural designs, performance evaluation metrics. The covers several models, including convolutional neural networks, generative adversarial physics-informed transformer diffusion reinforcement frameworks, emphasizing components improving reconstruction capabilities. Standard metrics are employed rigorously evaluate models' reliability efficacy producing high-performance results applicable across spatiotemporal data. findings emphasize essential role representing flows address ongoing related systems' high degrees freedom, precision demands, resilience error.

Language: Английский

---